Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    tipping and instability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /ar
    -0.06
     empt
    -0.06
     disin
    -0.06
     �
    -0.06
    Ζ
    -0.06
     Zd
    -0.06
    letes
    -0.06
    τίου
    -0.06
    _VO
    -0.06
    \\\
    -0.06
    POSITIVE LOGITS
    level
    0.07
    simulate
    0.07
     numeros
    0.07
    Accessor
    0.07
    ouncy
    0.07
    sparse
    0.07
    objective
    0.07
     изготов
    0.06
     }}
↵
    0.06
    .addActionListener
    0.06
    Act Density 0.073%

    No Known Activations